Image Aesthetics Assessment Based on Multi-stream CNN Architecture and Saliency Features
In this paper, we explore how higher-level perceptual information based on visual attention can be used for aesthetic assessment of images. We assume that visually dominant subjects in a photograph influence stronger aesthetic interest. In other words, visual attention may be a key to predicting pho...
Main Authors: | Hironori Takimoto, Fumiya Omori, Akihiro Kanagawa |
---|---|
Format: | Article |
Language: | English |
Published: |
Taylor & Francis Group
2021-01-01
|
Series: | Applied Artificial Intelligence |
Online Access: | http://dx.doi.org/10.1080/08839514.2020.1839197 |
Similar Items
-
Study on relationship between composition and prediction of photo aesthetics using CNN
by: Daichi Sakaguchi, et al.
Published: (2022-12-01) -
Food Constituent Estimation for Lifestyle Disease Prevention by Multi-Task CNN
by: Sulfayanti F. Situju, et al.
Published: (2019-07-01) -
Anomaly Detection Using Siamese Network with Attention Mechanism for Few-Shot Learning
by: Hironori Takimoto, et al.
Published: (2022-12-01) -
The Application of FLICSP Algorithm Based on Multi-Feature Fusion in Image Saliency Detection
by: Zhixian Li, et al.
Published: (2024-01-01) -
Multi-Scale Adversarial Feature Learning for Saliency Detection
by: Dandan Zhu, et al.
Published: (2018-10-01)